Time Series Forecasting
TiRex
ONNX
AdminNXAI lukfischer commited on
Commit
43ebaaf
·
1 Parent(s): 63c7409

docs: align model card with GitHub README and documentation (#6)

Browse files

- docs: align model card with GitHub README and documentation (09d625d43e1a8e370cde476aa01b228456f37f00)
- docs: compact title and badge header for Hub rendering (ec386ada01e7c10b228da66de82fd64138c9c8a3)
- docs: remove extra spacing around badges (1dce4562d4d820fc703252df9d49d0276c752451)


Co-authored-by: Lukas Fischer <lukfischer@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +48 -17
README.md CHANGED
@@ -9,11 +9,27 @@ license_link: https://huggingface.co/NX-AI/TiRex/blob/main/LICENSE
9
  license_name: nx-ai-community-license
10
  ---
11
 
12
- # TiRex
 
 
 
 
 
 
 
 
 
13
 
14
  This repository provides the pre-trained forecasting model TiRex introduced in the paper
15
  [TiRex: Zero-Shot Forecasting across Long and Short Horizons with Enhanced In-Context Learning](https://arxiv.org/abs/2505.23719).
16
 
 
 
 
 
 
 
 
17
  TiRex is a 35M parameter pre-trained time series forecasting model based on [xLSTM](https://github.com/NX-AI/xlstm).
18
 
19
  ### Key Facts:
@@ -26,7 +42,7 @@ TiRex is a 35M parameter pre-trained time series forecasting model based on [xLS
26
 
27
  - **State-of-the-art Performance over Long and Short Horizons**:
28
  TiRex achieves top scores in various time series forecasting benchmarks, see [GiftEval](https://huggingface.co/spaces/Salesforce/GIFT-Eval) and [ChronosZS](https://huggingface.co/spaces/autogluon/fev-leaderboard).
29
- These benchmark show that TiRex provides great performance for both long and short-term forecasting.
30
 
31
  ## Documentation
32
  A detailed documentation of TiRex can be found here: https://nx-ai.github.io/tirex/
@@ -60,37 +76,48 @@ data = torch.rand((5, 128)) # Sample Data (5 time series with length 128)
60
  quantiles, mean = model.forecast(context=data, prediction_length=64)
61
  ```
62
 
63
- We provide an extended quick start example in [examples/quick_start_tirex.ipynb](./examples/quick_start_tirex.ipynb).
64
- This notebook also shows how to use the different input and output types of you time series data.
65
  You can also run it in [Google Colab](https://colab.research.google.com/github/NX-AI/tirex/blob/main/examples/quick_start_tirex.ipynb).
66
 
67
- We provide notebooks to run the benchmarks: [GiftEval](./examples/gifteval/gifteval.ipynb) and [Chronos-ZS](./examples/chronos_zs/chronos_zs.ipynb).
68
 
69
  ## TiRex Classification Model
 
70
 
71
- For detailed instructions on using TiRex classification model please visit our [documentation page](https://nx-ai.github.io/tirex/how-to/classification/) and [quick start Notebook](./examples/quick_start_tirex_classification.ipynb).
72
 
73
- Paper: [Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification](http://arxiv.org/abs/2510.26777)
 
 
74
 
75
  ## TiRex Docker image
76
 
77
- For detailed instructions on building and running TiRex in a Docker container, see the [Docker README](./inference/README.md) or our [deployment documentation](https://nx-ai.github.io/tirex/deployment).
 
 
 
 
 
 
 
 
 
 
 
78
 
79
  ## Finetuning TiRex
80
- TiRex already provide state-of-the-art performance for zero-shot prediction. Hence, you can use it without training on your own data.
81
 
82
  If you are interested in models fine-tuned on your data or with different pretraining, please contact us at [contact@nx-ai.com](mailto:contact@nx-ai.com)
83
 
84
- ## Troubleshooting
85
- If you have problems please check the [documentation](https://nx-ai.github.io/tirex/) and feel free to create a GitHub issue or start a discussion.
86
-
87
 
88
  ## CUDA Kernels
89
 
90
- Tirex can use custom CUDA kernels for the sLSTM cells.
91
  These CUDA kernels are compiled when the model is loaded the first time.
92
  The CUDA kernels require GPU hardware that support CUDA compute capability 8.0 or later.
93
- We also highly suggest to use the provided [conda environment spec](./requirements_cu124.yaml).
94
  The CUDA kernels are automatically used when the xlstm package is installed.
95
 
96
  To install TiRex with the CUDA kernels run:
@@ -136,20 +163,24 @@ If you use TiRex in your research, please cite our work:
136
  title = {{{TiRex}}: {{Zero-Shot Forecasting Across Long}} and {{Short Horizons}} with {{Enhanced In-Context Learning}}},
137
  author = {Andreas Auer and Patrick Podest and Daniel Klotz and Sebastian B{\"o}ck and G{\"u}nter Klambauer and Sepp Hochreiter},
138
  booktitle = {The Thirty-Ninth Annual Conference on Neural Information Processing Systems},
139
- year = {2025}
140
  url = {https://arxiv.org/abs/2505.23719},
141
  }
142
  ```
143
  ```bibtex
144
  @inproceedings{auer:25tirexclassification,
145
  title = {Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification},
146
- author = {Andreas Auer and Daniel Klotz and Sebastinan B{\"o}ck and Sepp Hochreiter},
147
  booktitle = {NeurIPS 2025 Workshop on Recent Advances in Time Series Foundation Models (BERT2S)},
148
  year = {2025},
149
  url = {https://arxiv.org/abs/2510.26777},
150
  }
151
  ```
152
 
 
 
 
 
153
  ## License
154
 
155
- TiRex is licensed under the [NXAI community license](./LICENSE).
 
9
  license_name: nx-ai-community-license
10
  ---
11
 
12
+ <h1 align="center">TiRex: Zero-Shot Forecasting across Long and Short Horizons</h1>
13
+
14
+ <p align="center">
15
+ <a href="https://arxiv.org/abs/2505.23719"><img style="margin:2px 0;display:inline-block" src="https://img.shields.io/static/v1?label=Paper&message=2505.23719&color=B31B1B&logo=arXiv" alt="Paper"></a>
16
+ <a href="https://github.com/NX-AI/tirex"><img style="margin:2px 0;display:inline-block" src="https://img.shields.io/badge/GitHub-NX--AI%2Ftirex-181717?logo=github" alt="GitHub"></a>
17
+ <a href="https://pypi.org/project/tirex-ts/"><img style="margin:2px 0;display:inline-block" src="https://img.shields.io/pypi/v/tirex-ts?color=blue" alt="PyPI"></a>
18
+ <a href="https://pepy.tech/projects/tirex-ts"><img style="margin:2px 0;display:inline-block" src="https://static.pepy.tech/personalized-badge/tirex-ts?period=total&units=INTERNATIONAL_SYSTEM&left_color=GREY&right_color=BLUE&left_text=downloads" alt="PyPI Downloads"></a>
19
+ <a href="https://huggingface.co/NX-AI/TiRex/blob/main/LICENSE"><img style="margin:2px 0;display:inline-block" src="https://img.shields.io/badge/license-nxai_community-green" alt="License"></a>
20
+ <a href="https://nx-ai.github.io/tirex/"><img style="margin:2px 0;display:inline-block" src="https://img.shields.io/website?url=https%3A%2F%2Fnx-ai.github.io%2Ftirex%2F&label=docs&up_message=online&up_color=green&down_message=offline&down_color=red" alt="docs"></a>
21
+ </p>
22
 
23
  This repository provides the pre-trained forecasting model TiRex introduced in the paper
24
  [TiRex: Zero-Shot Forecasting across Long and Short Horizons with Enhanced In-Context Learning](https://arxiv.org/abs/2505.23719).
25
 
26
+ > **TiRex-2:** A newer generation of this model is available, extending TiRex with native
27
+ > multivariate forecasting and past/future-known covariates. See the
28
+ > [TiRex-2 repository](https://github.com/NX-AI/tirex-2) and
29
+ > [paper](https://arxiv.org/abs/2607.01204).
30
+
31
+ ## TiRex Model
32
+
33
  TiRex is a 35M parameter pre-trained time series forecasting model based on [xLSTM](https://github.com/NX-AI/xlstm).
34
 
35
  ### Key Facts:
 
42
 
43
  - **State-of-the-art Performance over Long and Short Horizons**:
44
  TiRex achieves top scores in various time series forecasting benchmarks, see [GiftEval](https://huggingface.co/spaces/Salesforce/GIFT-Eval) and [ChronosZS](https://huggingface.co/spaces/autogluon/fev-leaderboard).
45
+ These benchmarks show that TiRex provides great performance for both long and short-term forecasting.
46
 
47
  ## Documentation
48
  A detailed documentation of TiRex can be found here: https://nx-ai.github.io/tirex/
 
76
  quantiles, mean = model.forecast(context=data, prediction_length=64)
77
  ```
78
 
79
+ We provide an extended quick start example in [examples/quick_start_tirex.ipynb](https://github.com/NX-AI/tirex/blob/main/examples/quick_start_tirex.ipynb).
80
+ This notebook also shows how to use the different input and output types of your time series data.
81
  You can also run it in [Google Colab](https://colab.research.google.com/github/NX-AI/tirex/blob/main/examples/quick_start_tirex.ipynb).
82
 
83
+ We provide notebooks to run the benchmarks: [GiftEval](https://github.com/NX-AI/tirex/blob/main/examples/gifteval/gifteval.ipynb) and [Chronos-ZS](https://github.com/NX-AI/tirex/blob/main/examples/chronos_zs/chronos_zs.ipynb).
84
 
85
  ## TiRex Classification Model
86
+ [![Paper](https://img.shields.io/static/v1?label=Paper&message=2510.26777&color=B31B1B&logo=arXiv)](http://arxiv.org/abs/2510.26777)
87
 
88
+ For detailed instructions on using TiRex classification model please visit our [documentation page](https://nx-ai.github.io/tirex/how-to/classification/) and [quick start Notebook](https://github.com/NX-AI/tirex/blob/main/examples/quick_start_tirex_classification.ipynb).
89
 
90
+ ## TiRex Regression Model
91
+
92
+ For detailed instructions on using TiRex regression model please visit our [documentation page](https://nx-ai.github.io/tirex/how-to/regression/) or our [quick start Notebook](https://github.com/NX-AI/tirex/blob/main/examples/quick_start_tirex_regression.ipynb).
93
 
94
  ## TiRex Docker image
95
 
96
+ For detailed instructions on building and running TiRex in a Docker container, see the [Docker README](https://github.com/NX-AI/tirex/blob/main/inference/README.md) or our [deployment documentation](https://nx-ai.github.io/tirex/deployment).
97
+
98
+ ## Model files
99
+
100
+ | File | Format | Notes |
101
+ | --- | --- | --- |
102
+ | [`model.ckpt`](https://huggingface.co/NX-AI/TiRex/blob/main/model.ckpt) | PyTorch checkpoint | Default. Loaded by `load_model("NX-AI/TiRex")`. |
103
+ | [`tirex.onnx`](https://huggingface.co/NX-AI/TiRex/blob/main/tirex.onnx) | ONNX | For optimized inference across different hardware platforms and frameworks. |
104
+
105
+ ## ONNX Model
106
+
107
+ TiRex is available as an ONNX model (`tirex.onnx` in this repository) for optimized inference across different hardware platforms and frameworks. See the [ONNX notebook](https://github.com/NX-AI/tirex/blob/main/examples/tirex_onnx.ipynb) for more details.
108
 
109
  ## Finetuning TiRex
110
+ TiRex already provides state-of-the-art performance for zero-shot prediction. Hence, you can use it without training on your own data.
111
 
112
  If you are interested in models fine-tuned on your data or with different pretraining, please contact us at [contact@nx-ai.com](mailto:contact@nx-ai.com)
113
 
 
 
 
114
 
115
  ## CUDA Kernels
116
 
117
+ TiRex can use custom CUDA kernels for the sLSTM cells.
118
  These CUDA kernels are compiled when the model is loaded the first time.
119
  The CUDA kernels require GPU hardware that support CUDA compute capability 8.0 or later.
120
+ We also highly suggest to use the provided [conda environment spec](https://github.com/NX-AI/tirex/blob/main/requirements_cu124.yaml).
121
  The CUDA kernels are automatically used when the xlstm package is installed.
122
 
123
  To install TiRex with the CUDA kernels run:
 
163
  title = {{{TiRex}}: {{Zero-Shot Forecasting Across Long}} and {{Short Horizons}} with {{Enhanced In-Context Learning}}},
164
  author = {Andreas Auer and Patrick Podest and Daniel Klotz and Sebastian B{\"o}ck and G{\"u}nter Klambauer and Sepp Hochreiter},
165
  booktitle = {The Thirty-Ninth Annual Conference on Neural Information Processing Systems},
166
+ year = {2025},
167
  url = {https://arxiv.org/abs/2505.23719},
168
  }
169
  ```
170
  ```bibtex
171
  @inproceedings{auer:25tirexclassification,
172
  title = {Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification},
173
+ author = {Andreas Auer and Daniel Klotz and Sebastian B{\"o}ck and Sepp Hochreiter},
174
  booktitle = {NeurIPS 2025 Workshop on Recent Advances in Time Series Foundation Models (BERT2S)},
175
  year = {2025},
176
  url = {https://arxiv.org/abs/2510.26777},
177
  }
178
  ```
179
 
180
+ ## Intended use and limitations
181
+
182
+ This release supports time-series forecasting, classification, and regression as [documented](https://nx-ai.github.io/tirex/). High-risk applications under EU AI Act Article 6 are outside NXAI's intended purpose. NXAI has not validated this release for high-risk compliance. Users and integrators must assess suitability and meet their legal obligations. Unlawful uses, including those prohibited by EU AI Act Article 5, are not permitted. See the [Intended Use Notice](https://github.com/NX-AI/tirex/blob/main/INTENDED_USE.md) for details. It does not change the licence or statutory obligations.
183
+
184
  ## License
185
 
186
+ TiRex is licensed under the [NXAI community license](https://huggingface.co/NX-AI/TiRex/blob/main/LICENSE).